Exploring biologically inspired shallow model for visual classification | |
Tang, Tang; Qiao, Hong | |
刊名 | SIGNAL PROCESSING |
2014-12-01 | |
卷号 | 105页码:1-11 |
关键词 | Biologically inspired model Visual classification Max-pooling Shallow model |
英文摘要 | Visual classification has long been a major challenge for computer vision. In recent years, biologically inspired visual models have raised great interests. However, most of the related studies mainly focus on learning features and representations from very large scale dataset relying on deep network architecture, which is doomed to fail with limited training samples due to its high complexity. In this paper, it is found that aside from the deep architecture, two other biologically inspired mechanisms, the pooling and nonlinear operations, also contribute to the improvement of classification performance. Based on this perspective, a new classifier of shallow architecture is proposed, in which the both mechanisms are implemented with max operation. Moreover, the architecture is derived in a probabilistic perspective to further explain the underlying rationale thereof. To train the classifier, a supervised learning algorithm is devised to minimize the hinge loss function under the new architecture. Based on the manifold assumption of continuously transforming features, an unsupervised learning algorithm is also presented to learn the features used by the classifier. Finally, the method is compared against other classifiers on several image classification benchmarks. The results demonstrate the strength of the proposed method when the training data source is limited. (c) 2014 Elsevier B.V. All rights reserved. |
WOS标题词 | Science & Technology ; Technology |
类目[WOS] | Engineering, Electrical & Electronic |
研究领域[WOS] | Engineering |
关键词[WOS] | LOCAL BINARY PATTERNS ; OBJECT RECOGNITION ; FACE RECOGNITION ; REPRESENTATION ; CORTEX ; SCALE |
收录类别 | SCI |
语种 | 英语 |
WOS记录号 | WOS:000341347300001 |
内容类型 | 期刊论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/3043] |
专题 | 自动化研究所_复杂系统管理与控制国家重点实验室_机器人应用与理论组 |
作者单位 | Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China |
推荐引用方式 GB/T 7714 | Tang, Tang,Qiao, Hong. Exploring biologically inspired shallow model for visual classification[J]. SIGNAL PROCESSING,2014,105:1-11. |
APA | Tang, Tang,&Qiao, Hong.(2014).Exploring biologically inspired shallow model for visual classification.SIGNAL PROCESSING,105,1-11. |
MLA | Tang, Tang,et al."Exploring biologically inspired shallow model for visual classification".SIGNAL PROCESSING 105(2014):1-11. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论